metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya1_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8397297297297297
Boya1_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold2
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.6549
- Accuracy: 0.8397
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4334 | 1.0 | 923 | 0.4261 | 0.8314 |
0.3478 | 2.0 | 1846 | 0.4091 | 0.8357 |
0.2025 | 3.0 | 2769 | 0.6347 | 0.8408 |
0.0819 | 4.0 | 3692 | 0.8142 | 0.8341 |
0.1361 | 5.0 | 4615 | 1.0819 | 0.8441 |
0.0324 | 6.0 | 5538 | 1.3598 | 0.8427 |
0.0035 | 7.0 | 6461 | 1.6238 | 0.8430 |
0.0 | 8.0 | 7384 | 1.6312 | 0.8405 |
0.0002 | 9.0 | 8307 | 1.6680 | 0.8405 |
0.0001 | 10.0 | 9230 | 1.6549 | 0.8397 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2